{"id":"W4226137778","doi":"10.1109/tse.2022.3201209","title":"Flakify: A Black-Box, Language Model-Based Predictor for Flaky Tests","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; Canada Research Chairs; Western Canada Research Grid; Compute Canada","keywords":"Computer science; Debugging; Code coverage; Code (set theory); Set (abstract data type); Source code; White-box testing; Programming language; Software; Overhead (engineering); Black box; Test (biology); Machine learning; Artificial intelligence; Software development; Software construction","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002813454,0.003025534,0.00153294,0.003036439,0.0004998511,0.001785256,0.001978341,0.001584659,0.004328669],"category_scores_gemma":[0.01784386,0.0007128865,0.001314335,0.000973931,0.0009384812,0.002848697,0.002471065,0.003829167,0.003132715],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001184846,"about_ca_system_score_gemma":0.003598816,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007705452,"about_ca_topic_score_gemma":0.01019087,"domain_scores_codex":[0.9971291,0.0005796375,0.0001828468,0.0006614553,0.001089024,0.0003579643],"domain_scores_gemma":[0.9889017,0.007022789,0.001555927,0.0006268752,0.001389963,0.00050267],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001885064,0.001275659,0.07272731,0.0007249489,0.0003329514,0.0007492206,0.0003475074,0.3553134,0.02505508,0.005826243,0.02376752,0.5119951],"study_design_scores_gemma":[0.00004852785,0.0002759219,0.00267036,0.00005757024,0.00004519804,0.00009786372,0.00003069025,0.9843048,0.007010586,0.003085803,0.002325471,0.00004718559],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08964761,0.001524639,0.8467523,0.001142825,0.0002774688,0.0004203205,0.003173421,0.05426025,0.002801181],"genre_scores_gemma":[0.645858,0.0005903872,0.3338428,0.0009961568,0.0002098979,0.0008720935,0.008829081,0.00208439,0.006717304],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007705452,"threshold_uncertainty_score":0.0153212,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01371496591471183,"score_gpt":0.248779662007871,"score_spread":0.2350646960931591,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}